From polymath-engineering
Review a code change for correctness, simplification, and missing tests; produces a structured review summary keyed to the diff.
How this skill is triggered — by the user, by Claude, or both
Slash command
/polymath-engineering:code-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> Review a code change with two lenses: correctness (does it do what the PRD says?) and simplification (could it do the same with less?).
Review a code change with two lenses: correctness (does it do what the PRD says?) and simplification (could it do the same with less?).
polymath-engineering:code-review after feature-dev.feature-dev).Structured summary keyed to the diff:
Acceptance criteria coverage:
- AC1: PASS — test at <file>:<line>
- AC2: MISSING — no test for refund path
Correctness findings:
- <file>:<line> — boundary: rate-limit window misses requests exactly at start
Simplification findings:
- <file>:<line> — extracted helper has one caller; inline it
Security findings:
- <file>:<line> — user-supplied path concatenated without normalization
Test smell findings:
- <file>:<line> — assertion checks private member rather than observed behavior
No emoji, no praise filler. Findings only.
npx claudepluginhub mohammadbafkar/polymath --plugin polymath-engineeringProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.